{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:44:47Z","timestamp":1730231087009,"version":"3.28.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746798","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T15:50:34Z","timestamp":1651074634000},"page":"3263-3267","source":"Crossref","is-referenced-by-count":0,"title":["Self-Supervised Learning Method Using Multiple Sampling Strategies for General-Purpose Audio Representation"],"prefix":"10.1109","author":[{"given":"Ibuki","family":"Kuroyanagi","sequence":"first","affiliation":[{"name":"Line Corporation,Tokyo,Japan"}]},{"given":"Tatsuya","family":"Komatsu","sequence":"additional","affiliation":[{"name":"Line Corporation,Tokyo,Japan"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1113"},{"journal-title":"Representation learning with contrastive predictive coding","year":"2019","author":"van den oord","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","article-title":"Curl: Contrastive unsupervised representations for reinforcement learning","author":"laskin","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning Vienna Austria PMLR 119"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054548"},{"key":"ref16","article-title":"Vq-wav2vec: Self-supervised learning of discrete speech representations","author":"baevski","year":"2020","journal-title":"Proc ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1242"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461684"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"journal-title":"Self-supervised audio representation learning for mobile devices","year":"2019","author":"tagliasacchi","key":"ref28"},{"key":"ref4","first-page":"45","article-title":"Acoustic Event Detection Method Using Semi-Supervised Non-Negative Matrix Factorization with Mixtures of Local Dictionaries","author":"komatsu","year":"2016","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events 2016 Workshop (DCASE2016)"},{"key":"ref27","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc ICLR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-383"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref29","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume":"119","author":"chen","year":"2020","journal-title":"Proc ICML"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"776","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"2017","journal-title":"Proc ICASSP"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref9","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics Human Language Technologies Volume 1 (Long and Short Papers)"},{"journal-title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition","year":"2020","author":"zhang","key":"ref1"},{"article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","year":"2018","author":"warden","key":"ref20"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8169985"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2778423"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461329"},{"journal-title":"Neural audio synthesis of musical notes with wavenet autoencoders","year":"2017","author":"engel","key":"ref23"},{"key":"ref26","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"CoRR"},{"key":"ref25","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume":"97","author":"tan","year":"2019","journal-title":"Proc ICML"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2022,5,23]]},"location":"Singapore, Singapore","end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746798.pdf?arnumber=9746798","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,15]],"date-time":"2022-08-15T16:09:23Z","timestamp":1660579763000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746798\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746798","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}